Pick the most valuable set of jobs for one crew when moving between sites costs time
Exact prompt
# Build the most valuable day schedule for one crew Inputs: `jobs.csv` (job_id, site, start, end, value_usd; times are HH:MM on the same day) and `rules.json` (`changeover_minutes`). Rules: - The crew does one job at a time and must do a job from its start to its end. - Between two consecutive jobs at different sites the crew needs at least `changeover_minutes` from the end of one to the start of the next. Consecutive jobs at the same site only need the next start to be at or after the previous end. - Choose the set of jobs with the highest total value. The data has exactly one best set. - what_if_value = the best total value if changeover_minutes were doubled. Write `out/schedule.json`: `{"jobs": ["<job_id>", ... in start order], "total_value": <usd>, "job_count": <int>, "what_if_value": <usd>}`. ## How this run works - Work on your own: nobody will answer questions in this task, and writing to `ask/` counts against the run. - Write only under `out/`. Create `out/` if it is missing. Inputs are synthetic; don't fetch anything from the network. - Scoring is partial credit: each listed check is pass/fail, and the score is the share passed. Numbers are compared to within 0.005 unless the task says otherwise.
Choose jobs for one crew from 22-28 timed offers across four sites. Moving between different sites needs a changeover gap; staying on one site does not. Return the unique best set and the best value if the gap doubled. Every seed is drawn so that earliest-finish-first and highest-value-first greedy rules are strictly worse than the optimum, and ignoring changeovers gives a different set. Original benchmark task written for usecaserank.com (not based on a specific public post). Headless, offline run on a reproducible fixture. Each run's notes say how its cost was measured (estimates are marked). Folder-restore note: this run's output files under work/out/ were lost in a 1:22 AM ET restore on Oct 21, 2026. The trace, step-in exchanges and output-hash list were checked against the recorded SHA-256 values and match; the hashes of the individual output files inside that list can no longer be recomputed. Measured data unchanged.
Success criteria: optimal_jobs optimal_value changeover_respected what_if_doubled_gap
Best model for this task so far: Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) (success, $0.0039, 13s).
All runs (4)
75% pass rate across 4 eligible runs: 3 pass, 0 partial, 1 fail. Partial and failed runs are listed below with everything else.ⓘ
| Model | Cost | Time | Step-insⓘ | Autonomy | Outcome | Trustⓘ | Date | Compare |
|---|---|---|---|---|---|---|---|---|
| DDeepSeek V3.2 (Venice)thinking on | $0.03 | 11m | 0 | Fully autonomous | fail | Trust 80% | 2026-10-28 | |
| AClaude Opus 5.5default · thinking on | $0.11 | 17s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-21 | |
| AClaude Haiku 5.5default · thinking on | $0.0039 | 13s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-21 | |
| AClaude Sonnet 5.5default · thinking off | $0.04 | 9s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-21 |
Embed this result
A live badge for this use case. It links back here and updates as new runs are published.
Get new runs and ranking changes weekly
Which models got better or cheaper on real tasks like this one.